© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 163562
    Prev
    Next
    INDEX
    Explanations

    exercises lead

    np_acts-logits-general · gemini-2.5-flash-lite

    become, urine, artist, learning, 1, designer, clusters, prevent, woman

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    4
    0.51
    equipped
    0.49
    装備
    0.46
     wyposaż
    0.44
     kwenye
    0.44
     inscrit
    0.44
    3
    0.43
     dilengkapi
    0.42
    faite
    0.42
     உடன்
    0.42
    POSITIVE LOGITS
    าร์
    0.55
     стр
    0.49
     डियर
    0.49
    ী
    0.46
    日本人
    0.46
    FindFileData
    0.46
    ึ
    0.46
    듑
    0.45
    िट
    0.45
    ंतर
    0.44
    Activations Density 0.000%

    No Known Activations